CrewAI MCP Adapter
by dshivendra
A Python library that extends CrewAI's adapter ecosystem with Model Context Protocol (MCP) integration. It provides tooling for custom agent and tool development, enabling seamless interaction with MCP-compliant services.
Last updated: N/A
What is CrewAI MCP Adapter?
CrewAI MCP Adapter is a Python library facilitating the integration of CrewAI with Model Context Protocol (MCP). It allows developers to create custom agents and tools that can interact with MCP servers and leverage their functionalities within CrewAI workflows.
How to use CrewAI MCP Adapter?
To use the adapter, install it via pip. Then, connect to an MCP server using the CrewAIAdapterClient
. Define agents with tools obtained from the client and execute tasks within a CrewAI crew. Refer to the documentation for detailed examples and API usage.
Key features of CrewAI MCP Adapter
Native CrewAI Integration
MCP Protocol Support
Easy Adapter Extension
Type-Safe Implementation
JSON Schema Validation
Async/Await Support
Detailed Execution Metadata
Use cases of CrewAI MCP Adapter
Integrating external models into CrewAI
Developing custom tools for agents
Enabling communication between agents and external services
Creating complex AI workflows with specialized tools
Executing tasks leveraging context-aware models
FAQ from CrewAI MCP Adapter
What is Model Context Protocol (MCP)?
What is Model Context Protocol (MCP)?
MCP is a protocol designed for interaction with AI models and tools, providing a standard way to pass context and receive results.
How do I install the CrewAI MCP Adapter?
How do I install the CrewAI MCP Adapter?
You can install it using pip install crewai-adapters
.
What Python version is supported?
What Python version is supported?
Python 3.11 or higher is required.
Can I contribute to the project?
Can I contribute to the project?
Yes, contributions are welcome! Please submit a Pull Request.
Where can I find detailed documentation?
Where can I find detailed documentation?
Detailed documentation can be found in the docs/
directory, including a getting started guide, API reference, and examples.